crossdelenna
/

whisper-base.en

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

crossdelenna commited on Apr 2, 2023

Commit

b91385a

•

1 Parent(s): bb7f99c

update model card README.md

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [crossdelenna/whisper-base.en](https://huggingface.co/crossdelenna/whisper-base.en) on the None dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0001
-- Wer: 0.1498
 ## Model description
@@ -50,10 +50,10 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.0005        | 2.0   | 500  | 0.0014          | 0.3318 |
-| 0.0028        | 4.0   | 1000 | 0.0006          | 0.2676 |
-| 0.001         | 6.0   | 1500 | 0.0004          | 0.1713 |
-| 0.0001        | 8.0   | 2000 | 0.0001          | 0.1498 |
 ### Framework versions

 This model is a fine-tuned version of [crossdelenna/whisper-base.en](https://huggingface.co/crossdelenna/whisper-base.en) on the None dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0001
+- Wer: 0.1391
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.0007        | 2.0   | 500  | 0.0012          | 0.3639 |
+| 0.0016        | 4.0   | 1000 | 0.0002          | 0.1605 |
+| 0.0001        | 6.0   | 1500 | 0.0001          | 0.1391 |
+| 0.0001        | 8.0   | 2000 | 0.0001          | 0.1391 |
 ### Framework versions